Diaphragma sellae sinking can predict the onset of hyponatremia after transsphenoidal surgery for pituitary adenomas

Machine learning algorithms for predicting delayed hyponatremia after transsphenoidal surgery for patients with pituitary adenoma

This study aimed to develop and validate machine learning (ML) models to predict the occurrence of delayed hyponatremia after transsphenoidal surgery for pituitary adenoma. We retrospectively collected clinical data on patients with pituitary adenomas treated with transsphenoidal surgery between January 2010 and December 2020. From January 2021 to December 2022, patients with pituitary adenomas were prospectively enrolled. We trained seven ML models to predict delayed hyponatremia using the clinical variables in the training set. The final model was internally validated using a test set and a prospective dataset. The SHapley Additive exPlanations (SHAP) algorithm was used to determine the significance of each variable in the occurrence of delayed hyponatremia. In the training dataset, the best predictive performance was observed for XGBoost (area under the ROC curve; AUC = 0.821), followed by Random Forest (AUC = 0.8), Logistic Regression (AUC = 0.793), Support Vector Machine (AUC = 0.776), naïve Bayes (AUC = 0.774), K-Nearest Neighbors (AUC = 0.742), and Decision Tree (AUC = 0.717). The AUC of the XGBoost model for the test and prospective datasets are 0.831 and 0.785, respectively. The differences in pituitary stalk deviation angle, the "measurable pituitary stalk" length before and after surgery, and blood sodium concentration between preoperative and postoperative day 2 were important variables for predicting delayed hyponatremia as determined by the SHAP algorithm. The XGBoost model was best able to predict delayed hyponatremia after transsphenoidal surgery for pituitary adenomas. The differences in pituitary stalk deviation angle, pre- versus postoperative "measurable pituitary stalk" length, and pre- versus postoperative day 2 blood sodium concentrations were important variables for predicting delayed hyponatremia.

Early Postoperative Magnetic Resonance Imaging for Transsphenoidal Pituitary Surgery: A Systemic Literature Review and the Proposed Imaging Algorithm

Current neurosurgical consensus guidelines recommend that the first radiologic study to evaluate the extent of pituitary tumor resection be performed 3-4 months after surgery, defined as late postoperative (LPO) magnetic resonance imaging (MRI), and include fat-suppressed T1 and T2 sequences. The current guidelines supporting LPO MRI stem from older studies which claim that imaging <3 months postoperatively, defined as early postoperative (EPO), cannot be reliably interpreted due to acute postoperative changes. Several new technical and technological innovations that emerged since the promulgation of these guidelines may allow neurosurgeons to evaluate the extent of pituitary adenoma resection within a shorter timeframe, with higher resolution, and with greater certainty of the surrounding anatomy. We therefore sought to develop an evidence-based imaging algorithm, with regard to timing, magnetic field strength, and choice of views, for postoperative MRI following transsphenoidal pituitary adenoma resection by performing a systematic review of the available literature.

Predictive modeling of arginine vasopressin deficiency after transsphenoidal pituitary adenoma resection by using multiple machine learning algorithms

This study aimed to predict arginine vasopressin deficiency (AVP-D) following transsphenoidal pituitary adenoma surgery using machine learning algorithms. We reviewed 452 cases from December 2013 to December 2023, analyzing clinical and imaging data. Key predictors of AVP-D included sex, tumor height, preoperative and postoperative changes in sellar diaphragm height and pituitary stalk length, preoperative ACTH levels, changes in ACTH levels, and preoperative cortisol levels. Six machine learning algorithms were tested: logistic regression (LR), support vector classification (SVC), random forest (RF), decision tree (DT), k-nearest neighbors (KNN), and extreme gradient boosting (XGBoost). After cross-validation and parameter optimization, the random forest model demonstrated the highest performance, with an accuracy (ACC) of 0.882 and an AUC of 0.96. The decision tree model followed, achieving an accuracy of 0.843 and an AUC of 0.95. Other models showed lower performance: LR had an ACC of 0.522 and an AUC of 0.54; SVC had an ACC of 0.647 and an AUC of 0.67; KNN achieved an ACC of 0.64 and an AUC of 0.70; and XGBoost had an ACC of 0.794 and an AUC of 0.91. The study found that a shorter preoperative pituitary stalk length, significant intraoperative stretching, and lower preoperative ACTH and cortisol levels were associated with a higher likelihood of developing AVP-D post-surgery.

Visual outcomes and optimal timing for repeat surgery in cases of postoperative hematoma following transsphenoidal surgery for pituitary neuroendocrine tumors: A retrospective cohort study

OBJECTIVE

To investigate the visual outcomes and optimal timing for repeat surgery in cases of postoperative hematoma following transsphenoidal surgery for pituitary neuroendocrine tumors (PitNETs).

METHODS

A retrospective study was conducted on 28 patients who developed evident postoperative hematoma out of a total of 9,010 patients. The hematomas were classified into three types based on their CT appearance. Type 1a - mild high density with no tension, Type 1b - thin-layer high density; Type 2a - solid high density with large empty cavities, Type 2b - solid high density with small empty cavities; Type 3 -solid high density with no cavity showing high tension. Patient data were collected for analysis.

RESULTS

The study cohort comprised 10 female and 18 male patients, with a mean age of 51.5±11.9 years. Most patients presented with large adenomas (median diameter 36mm). Postoperative visual sight improved in 12 patients, remained stable in 11 patients, and worsened in 5 patients. Notably, no patients experienced worsened visual sight beyond twenty-four hours after the operation. Among the five patients with visual deterioration, four had CT type 3 hematoma (4/6, 66.7%), and one had CT type 2b hematoma (1/9, 11.1%). Patients in the type 3 CT group were significantly more prone to experience visual deterioration compared to those in the type 2 group (odds ratio [OR] 2.154 [95% CI 1.858-611.014], P=.027). Four patients underwent repeat surgery after visual deterioration, resulting in visual improvement following a prolonged recovery period. Postoperative hematoma had limited impact on pituitary dysfunction and hyponatremia.

CONCLUSION

Our study reveals a significant association between postoperative hematoma CT types and visual deterioration. For patients with stable visual sight and type 1 or 2a hematoma, conservative strategies may be considered. Conversely, type 2b and 3 patients are at higher risk of visual deterioration, especially within the first 24 hours after the operation. Consequently, early reoperation before vision worsens may be a prudent approach to reduce risks and improve visual outcomes, particularly in type 3 patients.

Incidence of postoperative hyponatremia after endoscopic endonasal pituitary transposition for skull base pathologies

PURPOSE

Pituitary transposition is a novel surgical approach to access the retroinfundibular space and interpeduncular cistern. Few studies have evaluated post-surgical outcomes, including incidence of hyponatremia, following pituitary transposition.

METHODS

This is a retrospective study including 72 patients who underwent endoscopic endonasal surgery involving pituitary transposition for non-pituitary derived tumors over a decade at the University of Pittsburgh Medical Center. Anterior pituitary deficiencies and replacement therapy, tumor pathology and pre-operative serum sodium (Na) were recorded. Na was assessed at postoperative day 1, 3, 5, 7, and 10. Anatomical/surgical parameters included sellar height, sellar access angle to approach the tumor, and cranial extension of the tumor above the sellar floor (B) compared to the height of the gland (A) (B/A). T-test (normally distributed variables) and Wilcoxon rank-sum test (not-normally distributed) were applied for mean comparison. Logistic regression analyzed correlations between anatomical/surgical parameters and postoperative hyponatremia.

RESULTS

55.6% of patients developed post-operative transient hyponatremia. Two patients (5%) developed severe hyponatremia (sodium level < 120 mmol/L). Eleven (15.3%) patients required desmopressin replacement immediately post-operatively, and 2 other patients needed desmopressin after discharge and after sodium nadir developed. Hyponatremia was inversely associated with sellar access angle (p = 0.02) and the tumor cranial extension above the sellar floor showing a trend towards significance (p = 0.09).

CONCLUSION

More than half of patients who had pituitary transposition developed transient hyponatremia. Hyponatremia was more common in those with narrower sellar access angle and smaller cranial extension of the tumor above the sellar floor. Anatomical/surgical parameters may allow risk-stratification for post-operative hyponatremia following pituitary transposition.

Pituitary Stalk Stretch Predicts Postoperative Diabetes Insipidus After Pituitary Macroadenoma Transsphenoidal Resection

BACKGROUND

Manipulation of the pituitary stalk, posterior pituitary gland, and hypothalamus during transsphenoidal pituitary adenoma resection can cause disruption of water electrolyte regulation leading to diabetes insipidus (DI).

OBJECTIVE

To determine whether pituitary stalk stretch is an independent risk factor for postoperative DI after pituitary adenoma resection.

METHODS

A retrospective review was performed of patients undergoing endoscopic endonasal resection of pituitary macroadenoma between July 2010 and December 2016 by a single neurosurgeon. We analyzed preoperative and postoperative imaging metrics to assess predictors for postoperative DI.

RESULTS

Of the 234 patients undergoing resection, 41 (17.5%) developed postoperative DI. DI was permanent in 10 (4.3%) and transient in 31 (13.2%). The pituitary stalk stretch, measured as the change in stalk length from preoperative to postoperative imaging, was greater in the DI compared with the non-DI group (10.1 mm vs 5.9 mm, P < .0001). The pituitary stalk stretch was associated with DI with significant difference in mean pituitary stalk stretch between non-DI group vs DI group (5.9 mm vs 10.1 mm, P < .0001). Multivariate analysis revealed that pituitary stalk stretch >10 mm was a significant independent predictor of postoperative DI [odds ratios = 2.56 (1.10-5.96), P = .029]. When stratified into transient and permanent DI, multivariable analysis showed that pituitary stalk stretch >10 mm was a significant independent predictor of transient DI [odds ratios = 2.71 (1.0-7.1), P = .046] but not permanent DI.

CONCLUSION

Postoperative pituitary stalk stretch after transsphenoidal pituitary adenoma surgery is an important factor for postoperative DI. We propose a reconstruction strategy to mitigate stalk stretch.

Pituitary stalk changes on magnetic resonance imaging following pituitary adenoma resection using a transsphenoidal approach

Objective

We aimed to investigate the magnetic resonance imaging (MRI) findings and clinical significance of position and changes in morphology of the pituitary stalk following pituitary adenoma (PA) resection using a transsphenoidal approach.

Methods

We collected clinical and MRI data of 108 patients with PA after transsphenoidal surgery. Diameter, length, and coronal deviation of the pituitary stalk were measured pre-, post-, and mid-term post-operatively, to observe pituitary stalk morphology.

Results

Of 108 patients, 53 pituitary stalks were recognisable pre-operatively. The angle between the pituitary stalk and the median line was 7.22°-50.20° (average, 25.85°) in 22 patients with left-sided pituitary stalks and 5.32°-64.05° (average, 21.63°) in 20 patients with right-sided pituitary stalks. Of 42 patients with preoperative pituitary stalk deviation, 41 had an early postoperative recovery and 1 had increased deviation. In the mid-term postoperative period, 21 of 42 patients had pituitary stalks located centrally. In 53 patients, the pituitary stalk length was 1.41-11.74 mm (mean, 6.12 mm) pre-operatively, 3.61-11.63 mm (mean, 6.93 mm) in the early postoperative period, and 5.37-17.57 mm (mean, 8.83 mm) in the mid-term postoperative period. In the early postoperative period, 58 (53.70%) patients had posterior pituitary bright spots (PPBS) and 28 (25.92%) had diabetes insipidus (DI).

Conclusion

Pre-operatively, the pituitary stalk was compressed and thinned. Post-operatively, it could be stretched to a "normal state", and its position showed a gradual centring trend. Post-operatively, the length of the pituitary stalk gradually increased. The PPBS in the early postoperative period negatively correlated with postoperative DI.

Change in the pituitary stalk deviation angle after transsphenoidal surgery can predict the development of diabetes insipidus for pituitary adenomas

Purpose

We aimed to assess the factors influencing the development of diabetes insipidus after transsphenoidal surgery for pituitary adenomas.

Methods

A retrospective analysis was conducted on the clinical data of patients with pituitary adenomas who underwent transsphenoidal surgery. The predictors of postoperative diabetes insipidus were determined using statistical analysis.

Results

Of the 415 patients who underwent microscopic transsphenoidal surgery for pituitary adenomas, 196 experienced postoperative diabetes insipidus. The sinking depth of the diaphragma sellae and the difference between the preoperative and postoperative pituitary stalk deviation angles in the diabetes insipidus group were greater than those in the non-diabetes insipidus group. Logistic regression analysis showed that the risk of diabetes insipidus after transsphenoidal surgery was higher in patients with a larger difference in their pituitary stalk deviation angles (odds ratio = 2.407, 95% CI = 1.335-4.342; P = 0.004).

Conclusion

The difference in the pituitary stalk deviation angle could predict the onset of diabetes insipidus after transsphenoidal surgery for pituitary adenomas.

Predictive factors for delayed hyponatremia after transsphenoidal surgery in patients with Rathke's cleft cysts

Purpose

We aimed to assess factors influencing the occurrence of delayed hyponatremia after transsphenoidal surgery in patients with Rathke's cleft cysts (RCCs).

Methods

We retrospectively collected the clinical data of patients who underwent transsphenoidal surgery for RCCs from January 2014 to January 2022. Univariate and multivariate analyses were used to determine the factors influencing the occurrence of postoperative delayed hyponatremia.

Results

Of the 78 microscopic transsphenoidal surgery recipients with RCCs, 15 experienced postoperative delayed hyponatremia. There were 35 men and 43 women, and mean age was 43.75 ± 14.95 years. The clinical manifestations of RCCs were headache (62 cases, 79.5%), visual dysfunction (35 cases, 44.9%), endocrine dysfunction symptoms (12 cases, 15.4%). After transsphenoidal surgery, 93.5% (58/62) had improvements in headache, and 97.1% (34/35) had improved or resolved compressive visual symptoms. Delayed hyponatremia occurred on average on day 6.46 and lasted on average for 4.40 days. Logistic regression analysis showed that the independent influencing factor of delayed hyponatremia after transsphenoidal surgery in patients with RCCs was postoperative diaphragma sellae height.

Conclusion

Postoperative diaphragma sellae height was identified as an independent influencing factor for delayed hyponatremia after transsphenoidal surgery in patients with RCCs.

Risk factors for delayed postoperative hyponatremia in patients with non-functioning pituitary adenomas undergoing transsphenoidal surgery: A single-institution study

Purpose

We aimed to assess factors influencing the occurrence of delayed hyponatremia after transsphenoidal surgery (TSS) in patients with a non-functional pituitary adenoma (NFPA).

Methods

We retrospectively collected the clinical data of patients who underwent TSS for NFPA between January 2016 and January 2021. The pituitary region was preoperatively scanned with 3.0 T magnetic resonance imaging. The risk factors for delayed postoperative hyponatremia for NFPA were identified by univariate and multivariable logistic regression analysis.

Results

We selected 166 patients with NFPA who fulfilled the inclusion criteria. Delayed postoperative hyponatremia occurred in 28 patients and did not in 138. Multivariable logistic regression analyses demonstrated that higher odds of developing delayed postoperative hyponatremia were independently associated with larger craniocaudal dimension (OR = 1.128, P = 0.034), as well as preoperative hyperprolactinemia (OR = 2.618, P = 0.045) and larger preoperative pituitary stalk deviation angle (OR = 3.033, P = 0.022).

Conclusion

We identified the independent risk factors for delayed hyponatremia after TSS for NFPA; these included preoperative hyperprolactinemia, craniocaudal diameter, and preoperative pituitary stalk deviation angle.

Predictive factors for delayed hyponatremia after transsphenoidal surgery in patients with pituitary adenomas

Objective

The aim of this study was to evaluate the incidence and duration of delayed hyponatremia and to assess the factors influencing the development of delayed hyponatremia after transsphenoidal surgery (TSS) in pituitary adenomas.

Methods

We retrospectively analyzed the clinical data of patients with pituitary adenoma who underwent TSS. Univariable and multivariable statistics were carried out to identify factors independently associated with the occurrence of delayed hyponatremia.

Results

Of the 285 patients with pituitary adenoma who underwent microscopic TSS, 44 (15.4%) developed postoperative-delayed hyponatremia and 241 (84.6%) did not. The onset of delayed hyponatremia occurred an average of 5.84 days post-surgery and persisted for an average of 5.36 days. Logistic regression analysis showed the highest risk of delayed hyponatremia in patients with significant change in tumor cavity height (odds ratio (OR), 1.158; 95% CI, 1.062, 1.262; P = 0.001), preoperative hypothalamus-pituitary-thyroid axis hypofunction (OR, 3.112; 95% CI, 1.481, 6.539; P = 0.003), and significant difference in blood sodium levels before and 2 days after TSS (OR, 1.101; 95% CI, 1.005, 1.206; P = 0.039).

Conclusions

Preoperative hypothyroidism, difference in blood sodium levels before and 2 days after TSS, and the change in tumor cavity height after TSS played important roles in predicting postoperative-delayed hyponatremia onset in patients with pituitary adenomas.

Novel Nomograms to Predict Delayed Hyponatremia After Transsphenoidal Surgery for Pituitary Adenoma

OBJECTIVE

This study aimed to develop a nomogram of clinical variables and magnetic resonance imaging scans to predict delayed hyponatremia after transsphenoidal surgery for pituitary adenoma.

METHODS

Patients who underwent transsphenoidal surgery for pituitary adenoma in Fuzong Clinical Medical College of Fujian Medical University between January 2012 and December 2020 were retrospectively investigated. Medical records, MRI findings, and laboratory examination results were recorded as candidate variable predictors of delayed hyponatremia. A nomogram to predict delayed hyponatremia was formulated based on the multivariable model of risk factors. The predictive accuracy and discriminative ability of the nomogram were assessed using the receiver operating characteristic (ROC) curve, calibration plot, and decision curve analyses. The model underwent prospective validation in three medical centers with patients who underwent transsphenoidal surgery for pituitary adenoma between January 2021 and February 2022.

RESULTS

The model that incorporated the postoperative length of "measurable pituitary stalk," pituitary stalk deviation angle difference, postoperative diabetes insipidus, sinking depth of diaphragma sellae, and blood sodium level on the second postoperative day was developed and presented as the nomogram of the training cohort. The nomogram achieved area under the ROC curve (AUCs) of 0.806 and 0.849 for the training cohort and the testing cohort, respectively, and displayed good calibration. Decision curve analysis showed that the nomogram was clinically useful when the threshold probability was 13-96%.

CONCLUSIONS

We developed a nomogram to evaluate the individualized prediction of delayed hyponatremia after transsphenoidal surgery for pituitary adenomas.